Development and validation of a diagnostic model based on machine learning algorithms for the development of interstitial lung diseases in patients with rheumatoid arthritis / 中华风湿病学杂志

Objective:Screening factors that might influence rheumatoid arthritis (RA) complicating interstitial lung diseases (ILD) by constructing and validating a model for early diagnostic.Methods:The study subjects were composed of 712 RA patients in the Department of Rheumatology and Immunology of the Second Hospital of Shanxi Medical University during December 2019 to October 2022. Fifty-two variables such as their demographic data, clinical symptoms, and laboratory indexes were collected. Patients were categorized into RA-only group and RA-ILD group with or without the occurrence of ILD disease. After data preprocessing, subjects were randomly assigned to the modeling and validation groups in a 7:3 ratio.Univariate analysis comparing baseline characteristics of the two groups of patients. Feature selection was performed using LASSO and SVM-RFE regression algorithms.Screening indicators were analyzed by logistic regression and the results were used to develop a nomograms model for the early diagnosis of RA complicating interstitial lung disease; and the modeling group was evaluated for its performance for internal assessment of the model and internal validation using data from the validation group.Results:A total of 712 subjects participated in the study, of which 498 in the modeling group and 214 in the validation group. Univariate analysis showed that the differences between the two groups were statistically significant ( P<0.05) in 18 characteristic indexes, including male, gender, age, smoking history, drinking history, number of swollen joints, number of painful joints, use of prednisone, WBC, ESR, CRP, IL-2, IL-10, IL-17, TNF-α, INF-γ, AFA family, APF, and serum albumin. The LASSO algorithm identified 13 risk variables for RA-ILD, the SVM-RFE algorithm identified 12 variables for RA-ILD, and the intersecting risk variables were male, age, history of alcohol consumption, number of painful joints, prednisone acetate, IL-2, AFA family, TNF-α, serum albumin, and IL-10. The results of multifactorial logistic regression analysis confirmed that the differences between males [ OR(95% CI)=3.61(2.11, 6.18)], gender, age [ OR(95% CI)=1.05(1.03, 1.08)], number of painful joints [ OR(95% CI)=1.03(1.01, 1.06)], IL-2 [ OR(95% CI)=0.91 (0.84, 0.99)], and TNF-α[ OR (95% CI)=1.06 (1.02, 1.10)] were statistically significant ( P<0.05) and were independently influences on ILD complicated by RA. The modeling and validation groups that were used to construct early diagnostic Nomograms had high calibration curve accuracies, and the model had a high diagnostic power, which was mainly demonstrated by the receiver operating characteristic (ROC) area under the curve (AUC) and decision curve analysis(DCA), the model modeling group had an AUC of 0.76 (95% CI=0.71, 0.81), with net benefit rates of 3%~82% and 93%~99%, whereas the model validation group had an AUC of 0.71 (95% CI=0.64, 0.79), with net benefit rates of 5%~11%, 14%~60% and 85%~89%. Conclusion:Male, gender, age, number of painful joints, IL-2, and TNF-α are independent factors for RA complicated with ILD, and the Nomogram model constructed has good performance in early diagnosis of the disease.

Risk factors and predictive models for liver cancer after sustained virologic response in hepatitis C / 临床肝胆病杂志

Hepatitis C is one of the main causes of liver cancer. With the application of direct-acting antiviral agents， more than 95% of patients can achieve the eradication of hepatitis C virus and obtain sustained virologic response （SVR）. Effective antiviral therapy can change the natural course of hepatitis C and reduce the risk of liver cancer； however， some patients are still affected by age， sex， liver fibrosis， diabetes， hepatic steatosis， alcohol consumption， and genetic factors and become the high-risk population of liver cancer. Therefore， it is needed to further clarify and improve the identification and prediction of high-risk populations of liver cancer after SVR of hepatitis C. This article reviews the risk factors and predictive models for liver cancer after SVR in patients with hepatitis C， in order to provide a basis for identifying the high-risk population of liver cancer after SVR of hepatitis C in clinical practice.

Urinary microalbumin to creatinine ratio and α1-microglobulin to creatinine ratio and their influencing factors in people aged ≥40 years old in 10 counties of Shanxi province / 中华肾脏病杂志

Objective:To investigate urinary microalbumin to creatinine ratio (ACR) and α1-microglobulin to creatinine ratio (MCR) of people aged 40 years old and above in Shanxi province, and analyze the influencing factors of abnormal ACR and MCR, and to provide evidence for the prevention and control of chronic kidney diseases.Methods:It was a cross-sectional study. The data came from a screening study of chronic kidney diseases conducted by Shanxi Provincial People's Hospital from April to November 2019, involving aged 40 years old and above from 10 counties (Ningwu county, Yu county, Yangqu county, Lin county, Shouyang county, Zezhou county, Huozhou city, Hejin city, Linyi county and Ruicheng county) in Shanxi province. The related data were collected through questionnaire surveys, physical examinations, and blood and urine sample collection. Urinary α1-microglobulin, creatinine, and microalbuminuria were measured. Urinary ACR and MCR were calculated using urinary creatinine correction. ACR abnormality was defined as ≥30 mg/g, and MCR abnormality was defined as >23 mg/g. Covariate analysis was used to control confounding factors, and adjusted urinary ACR and MCR of 10 counties were calculated. Spearman correlation analysis and chi-square test were performed to analyze the factors associated with abnormal urinary ACR and MCR. Logistic regression analysis model was used to identify the influencing factors of abnormal urinary ACR and MCR.Results:A total of 12 285 residents were enrolled in the study, including 5 206 males (42.4%) and 7 079 females (57.6%). The median age was 58.0 (51.0, 66.0) years old. The median urinary ACR was 7.5 (4.5, 15.7) mg/g, and the median urinary MCR was 10.2 (6.4, 16.2) mg/g. A total of 1 572 individuals (12.80%) had urinary ACR abnormality and 1 450 individuals (11.80%) had urinary MCR abnormality. Yangqu county, Yuxian county, and Ningwu county had higher urinary ACR with (35.58±3.04) mg/g, (34.08±4.50) mg/g and (32.09±3.19) mg/g, respectively. The urinary MCR was generally similar among the 10 counties and Yangqu county had higher urinary MCR with (13.86±0.41) mg/g. In addition to Yu county, female individuals had higher urinary ACR compared to males in other counties, whereas female individuals had lower urinary MCR compared to males in 10 counties. Multivariate logistic regression analysis results showed that elevated triglyceride, fasting blood glucose, glycated hemoglobin, systolic blood pressure, diastolic blood pressure, age, body mass index and gender were independent influencing factors of abnormal urinary ACR and MCR (all P<0.05). Elevated blood homocysteine and low educational level were independent influencing factors of urinary MCR abnormality (both P<0.05). Conclusions:There are differences of gender and region in urinary ACR and MCR among individuals aged 40 years old and above in the 10 counties of Shanxi province. Triglyceride, fasting blood glucose, glycated hemoglobin, systolic blood pressure, diastolic blood pressure, age, gender, and body mass index are independent related factors of abnormal urinary ACR and MCR. Blood homocysteine and education level are independent related factors of abnormal urinary MCR.

Construction of intervention program for physical and mental adjustment for primary caregivers of cancer patients based on network cognitive behavior therapy / 中国实用护理杂志

Objective:Based on cognitive behavioral therapy, to construct a physical and mental adjustment intervention plan for the main caregiver of cancer patients through the network platform.Methods:Through evidence-based literature published from July 2012 to July 2022 screening and evaluation, combined with qualitative interviews for 10 primary caregivers of cancer patients, the intervention plan for physical and mental adjustment of the main caregivers of cancer patients was preliminarily formulated. After consultation with Delphi experts (15 cases) through two rounds, the intervention plan was finally determined.Results:In the two rounds of expert letter inquiries, 15 questionnaires were distributed and 15 valid questionnaires were recovered. The effective recovery rate was 100.00% and the expert authority coefficient were 0.89 and 0.90 in the two rounds of expert letter inquiries respectively, the Kendall harmony coefficients were 0.279 and 0.323 respectively, and the differences were all statistically significant ( P<0.01). The intervention plan for physical and mental adjustment ofthe main caregivers of cancer patients included 5 first-level indicators (basic knowledge, symptom education, home care knowledge, relaxation training, social support), 27 second-level indicatorsand 54 third-level indicators. Conclusions:The method of the psychosomatic regulation intervention program is scientific and practical, which can be initially applied to the psychological adjustment of the main caregivers of cancer patients, so as to provide a reference for improving their negative emotions.

Clinical features of patients with different types of acute drug-induced liver injury: A comparative analysis / 临床肝胆病杂志

ObjectiveTo investigate the clinical features of patients with different types of acute drug-induced liver injury (DILI) through a retrospective analysis. MethodsClinical data were collected from 790 patients who were diagnosed with acute DILI in Beijing YouAn Hospital and Beijing Tongren Hospital affiliated to Capital Medical University from December 2010 to March 2019, and according to the type of damaged target cell, the patients were divided into hepatocellular injury type group with 554 patients, cholestasis type group with 99 patients, and mixed type group with 137 patients. The patients were evaluated based on severity grade and score, clinical outcome, and Hy′s rule. An analysis of variance was used for comparison of normally distributed continuous data between three groups, and the least significant difference t-test was used for further comparison between two groups; the Kruskal-Wallis H test was used for comparison of non-normally distributed continuous data between groups. The chi-square test was used for comparison of categorical data between three groups. The Kruskal-Wallis H test was used for comparison of ranked data between three groups, and the Mann-Whitney U test was used for comparison between two groups. ResultsMost of the patients were female in all three groups, and the hepatocellular injury type group had a significantly higher proportion of female patients than the cholestasis type group (70.8% vs 54.5%, P＜0.05), and the Cholestasis type group had a significantly lower proportion of female patients than the mixed type group(54.5% vs 54.7%, P＜0.05). There were 244 patients with grade 3 hepatocellular injury type DILI (244/554, 44.4%), 56 patients with grade 3 cholestasis type DILI (56/99, 56.6%), and 46 patients with grade 3 mixed type DILI (46/137, 33.6%), and there was a significant difference between the three groups (χ2=36.589, P＜0.05). Drugs inducing liver injury included traditional Chinese medicine, Western medicine, combination of traditional Chinese medicine and Western medicine, and other drugs, among which traditional Chinese medicine was the most common cause of liver injury. There was a significant difference in the outcome at discharge between the patients with different types (H=14.390, P=0.001). Compared with the cholestasis type group, the hepatocellular injury type group had a significantly higher cure rate and significantly lower uncured rate and mortality rate (all P＜0.05). Among the 554 patients with hepatocellular injury type DILI, 388 (70.0%) met Hy′s rule and 166 (300%) did not meet Hy′s rule, and there was a significant difference in clinical outcome between these two groups (U=38 372.0, P=0.033). ConclusionDILI is more common in women, and most patients have hepatocellular injury type DILI. Traditional Chinese medicine is the main cause of liver injury. There is a high proportion of patients with severe DILI among the patients with hepatocellular injury type or cholestasis type. DILI often has good prognosis with a relatively low mortality rate. Hy′s rule cannot predict the death of patients with acute DILI.

Association of inosine triphosphate pyrophosphatase gene polymorphisms with ribavirin combined with direct-acting antiviral agent in treatment of hepatitis C patients with hemolytic anemia / 临床肝胆病杂志

Objective To investigate the influencing factors for ribavirin (RBV)-induced hemolytic anemia in the treatment of chronic hepatitis C, and to provide a reference for the early prediction of ribavirin-related hemolytic anemia in clinical practice. Methods A total of 49 patients with chronic hepatitis C who attended or were hospitalized in Hebei Petrochina Central Hospital from January 2018 to July 2019 and received antiviral therapy with direct-acting antiviral agent (DAA) and RBV were enrolled, with a major allele of C allele and a minor allele of A allele at the rs1127354 locus of the inosine triphosphate pyrophosphatase (ITPA) gene, and the patients with AA and AC genotypes were compared with those with CC genotype. During treatment, RBV was reduced to 600 mg when hemoglobin (Hb) level was < 100 g/L and was withdrawn when Hb level was < 85 g/L. Routine blood test, liver function, liver stiffness measurement, HCV RNA, HCV genotype, and ITPA genotype were measured before antiviral therapy, and the routine blood test was performed at weeks 2, 4, 8, and 12 of treatment. The Mann-Whitney U test was used for comparison of non-normally distributed continuous data between groups. Results A total of 49 patients were enrolled in this study, among whom 22 had chronic hepatitis C and 27 had liver cirrhosis, with a sustained virologic response (SVR) rate of 95.9%. The dose of RBV was reduced in 3 patients (2 in the AA/AC group and 1 in the CC group) due to anemia, and RBV was withdrawn in 3 patients (1 in the AA/AC group and 2 in the CC group); all these 6 patients had liver cirrhosis and finally achieved SVR. During the anti-HCV therapy with DAA+RBV, there was relatively mild RBV-related hemolysis, and the maximum reduction in Hb from baseline was compared between the patients with AA/AC genotype at ITPA rs1127354 and those with CC genotype, which showed no significant difference between the two groups ( Z =-0.18, P =0.87). Conclusion During the treatment with RBV+DAA, RBV is withdrawn or reduced for liver cirrhosis patients due to anemia, and no obvious statistical relation is observed between ITPA genotype and the maximum reduction in Hb from baseline. Therefore, detection of ITPA genotype before the application of RBV does not improve safety during treatment, and it is not recommended to perform conventional detection of ITPA gene polymorphisms.

Association of inosine triphosphate pyrophosphatase gene polymorphisms with ribavirin combined with direct-acting antiviral agent in treatment of hepatitis C patients with hemolytic anemia / 临床肝胆病杂志

Objective To investigate the influencing factors for ribavirin (RBV)-induced hemolytic anemia in the treatment of chronic hepatitis C, and to provide a reference for the early prediction of ribavirin-related hemolytic anemia in clinical practice. Methods A total of 49 patients with chronic hepatitis C who attended or were hospitalized in Hebei Petrochina Central Hospital from January 2018 to July 2019 and received antiviral therapy with direct-acting antiviral agent (DAA) and RBV were enrolled, with a major allele of C allele and a minor allele of A allele at the rs1127354 locus of the inosine triphosphate pyrophosphatase (ITPA) gene, and the patients with AA and AC genotypes were compared with those with CC genotype. During treatment, RBV was reduced to 600 mg when hemoglobin (Hb) level was < 100 g/L and was withdrawn when Hb level was < 85 g/L. Routine blood test, liver function, liver stiffness measurement, HCV RNA, HCV genotype, and ITPA genotype were measured before antiviral therapy, and the routine blood test was performed at weeks 2, 4, 8, and 12 of treatment. The Mann-Whitney U test was used for comparison of non-normally distributed continuous data between groups. Results A total of 49 patients were enrolled in this study, among whom 22 had chronic hepatitis C and 27 had liver cirrhosis, with a sustained virologic response (SVR) rate of 95.9%. The dose of RBV was reduced in 3 patients (2 in the AA/AC group and 1 in the CC group) due to anemia, and RBV was withdrawn in 3 patients (1 in the AA/AC group and 2 in the CC group); all these 6 patients had liver cirrhosis and finally achieved SVR. During the anti-HCV therapy with DAA+RBV, there was relatively mild RBV-related hemolysis, and the maximum reduction in Hb from baseline was compared between the patients with AA/AC genotype at ITPA rs1127354 and those with CC genotype, which showed no significant difference between the two groups ( Z =-0.18, P =0.87). Conclusion During the treatment with RBV+DAA, RBV is withdrawn or reduced for liver cirrhosis patients due to anemia, and no obvious statistical relation is observed between ITPA genotype and the maximum reduction in Hb from baseline. Therefore, detection of ITPA genotype before the application of RBV does not improve safety during treatment, and it is not recommended to perform conventional detection of ITPA gene polymorphisms.

The cut off value of liver stiffness measurement needs to be lowered to predict liver fibrosis after sustained virologic response in chronic hepatitis C patients / 临床肝胆病杂志

Objective To further verify the ability of noninvasive diagnostic method for liver fibrosis in predicting liver fibrosis in chronic hepatitis C patients followed up after sustained virologic response (SVR) based on liver biopsy. Methods A prospective cohort study was performed for the chronic hepatitis C patients who attended Beijing YouAn Hospital, Capital Medical University, from October 2015 to December 2017, and all patients were followed up regularly after SVR and underwent liver biopsy. The diagnostic efficiency of the noninvasive diagnostic method for liver fibrosis was verified based on pathological results. The receiver operating characteristic (ROC) curve was used to evaluate the ability of LSM, aspartate aminotransferase-to-platelet ratio index (APRI), and fibrosis-4 (FIB-4) in the diagnosis of liver fibrosis, and STATA and R language were used to compare the area under the ROC curve (AUC). Results A total of 96 patients were successfully enrolled. The LSM after SVR was significantly lower than that at baseline, and LSM had a significantly larger AUC than APRI (0.89 vs 0.67, P < 0.05) and FIB (0.89 vs 0.69, P < 0.05) in the diagnosis of liver cirrhosis after SVR. LSM at a cut-off value of 7.95 kPa, and based on the best specificity, the diagnosis of liver cirrhosis could be considered when LSM was greater than 9.15 kPa, with a positive likelihood ratio of 5.91%; progressive liver fibrosis could be excluded based on LSM < 6.85 kPa, with a negative predictive value of 0.98. Follow-up time and antiviral regimen had no influence on the diagnostic ability of LSM. Conclusion The cut off value of LSM needs to be lowered to predict liver fibrosis after SVR in chronic hepatitis C patients.

Progress of cervical cancer treatment / 肿瘤研究与临床

Cervical cancer has become the second leading cause of female cancer death around the world.The main treatment methods include surgery,radiotherapy and chemotherapy. The way to apply various treatment strategies more scientifically and rationally is the key to improve the curative effect. Comprehensive application of several treatment methods can reduce the adverse effects of radiotherapy and chemotherapy,and enhance the sensitivity to achieve the prospective therapeutic effect, and greatly improve the cure rate combined with survival rate.

Analysis on spatial distribution of tuberculosis in China, 2012-2014 / 中华流行病学杂志

Objective To analyze the spatial distribution of the incidence of tuberculosis (TB)in China from 2012 to 2014 and provide evidence for the prevention and control of TB.Methods The database of TB in China from 2012 to 2014 was established by using geographical information system,the spatial distribution map was drawn,trend analysis and spatial autocorrelation analysis were conducted to explore the spatial distribution pattern of TB and identify hot areas.Results The trend surface analysis showed that the incidence of TB decreased gradually from the west to the east in China,and the U type curve could reflect the TB distribution from the south to the north;Global spatial autocorrelation analysis showed the 2012-2014 global Moran's I were 0.366,0.364 and 0.358(P＜0.01),suggesting that the incidence of TB had a spatial clustering in China;Local Getis-OrdGi spatial autocorrelation analysis by ArcGIS software showed that there was 11 cluster areas,3 high incidence areas (Xinjiang,Tibet,Qinghai) and 8 low incidence areas (Beijing,Tianjin,Shanghai,Hebei,Inner Mongolia,Shanxi,Shandong,Jiangsu).Conclusion The incidence of TB had obviously spatial clustering characteristic,the areas at high risk were mainly in the northwestern and plateau area in China.

Analysis on spatial distribution of tuberculosis in China, 2012-2014 / 中华流行病学杂志

Objective To analyze the spatial distribution of the incidence of tuberculosis (TB)in China from 2012 to 2014 and provide evidence for the prevention and control of TB.Methods The database of TB in China from 2012 to 2014 was established by using geographical information system,the spatial distribution map was drawn,trend analysis and spatial autocorrelation analysis were conducted to explore the spatial distribution pattern of TB and identify hot areas.Results The trend surface analysis showed that the incidence of TB decreased gradually from the west to the east in China,and the U type curve could reflect the TB distribution from the south to the north;Global spatial autocorrelation analysis showed the 2012-2014 global Moran's I were 0.366,0.364 and 0.358(P＜0.01),suggesting that the incidence of TB had a spatial clustering in China;Local Getis-OrdGi spatial autocorrelation analysis by ArcGIS software showed that there was 11 cluster areas,3 high incidence areas (Xinjiang,Tibet,Qinghai) and 8 low incidence areas (Beijing,Tianjin,Shanghai,Hebei,Inner Mongolia,Shanxi,Shandong,Jiangsu).Conclusion The incidence of TB had obviously spatial clustering characteristic,the areas at high risk were mainly in the northwestern and plateau area in China.

Using the Tabu-search-algorithm-based Bayesian network to analyze the risk factors of coronary heart diseases / 中华流行病学杂志

Under the available data gathered from a coronary study questionnaires with 10 792 cases,this article constructs a Bayesian network model based on the tabu search algorithm and calculates the conditional probability of each node,using the Maximum-likelihood.Pros and cons of the Bayesian network model are evaluated to compare against the logistic regression model in the analysis of coronary factors.Applicability of this network model in clinical study is also investigated.Results show that Bayesian network model can reveal the complex correlations among influencing factors on the coronary and the relationship with coronary heart diseases.Bayesian network model seems promising and more practical than the logistic regression model in analyzing the influencing factors of coronary heart disease.

Using the Tabu-search-algorithm-based Bayesian network to analyze the risk factors of coronary heart diseases / 中华流行病学杂志

Under the available data gathered from a coronary study questionnaires with 10 792 cases,this article constructs a Bayesian network model based on the tabu search algorithm and calculates the conditional probability of each node,using the Maximum-likelihood.Pros and cons of the Bayesian network model are evaluated to compare against the logistic regression model in the analysis of coronary factors.Applicability of this network model in clinical study is also investigated.Results show that Bayesian network model can reveal the complex correlations among influencing factors on the coronary and the relationship with coronary heart diseases.Bayesian network model seems promising and more practical than the logistic regression model in analyzing the influencing factors of coronary heart disease.